Lane information determination method and device, equipment and storage medium

Abstract

The invention provides a method for determining lane information, and relates to the technical field of artificial intelligence, in particular to the technical fields of map navigation, automatic driving, intelligent traffic and the like. The method comprises the following steps: determining current map lane information corresponding to the current position of a vehicle from a high-precision map; determining current visual lane information corresponding to the current position from a visual image acquired by the vehicle; in response to determining that the current visual lane information is inconsistent with the current map lane information, correcting the current visual lane information according to lane information in a pre-constructed track database to obtain corrected current visual lane information; and in response to determining that the corrected current visual lane information is consistent with the current map lane information, generating target lane information corresponding to the current position. The method improves the accuracy of the lane information.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as map navigation, autonomous driving, and intelligent transportation, and in particular to a method, device, equipment, and storage medium for determining lane information. Background Art

[0002] With the advancement of technology, the function of car autonomous driving is constantly improving. In the process of car autonomous driving, the road model, as an important driving basis, has become one of the most important research objects. Among them, the lane line is an important part of the road model, and its perception raw data comes from a variety of sensors, including: front-view camera, surround-view camera, high-precision map, etc. Summary of the invention

[0003] The present disclosure provides a method, device, equipment and storage medium for determining lane information.

[0004] According to a first aspect of the present disclosure, a method for determining lane information is provided, including: determining current map lane information corresponding to a current position of a vehicle from a high-precision map; determining current visual lane information corresponding to the current position from a visual image collected by the vehicle; in response to determining that the current visual lane information is inconsistent with the current map lane information, correcting the current visual lane information according to lane information in a pre-constructed trajectory database to obtain corrected current visual lane information; in response to determining that the corrected current visual lane information is consistent with the current map lane information, generating target lane information corresponding to the current position.

[0005] According to a second aspect of the present disclosure, a lane information determination device is provided, comprising: a map information determination module, configured to determine current map lane information corresponding to the current position of a vehicle from a high-precision map; a visual information determination module, configured to determine current visual lane information corresponding to the current position from a visual image collected by the vehicle; an information correction module, configured to, in response to determining that the current visual lane information is inconsistent with the current map lane information, correct the current visual lane information according to lane information in a pre-constructed trajectory database to obtain corrected current visual lane information; and a target information determination module, configured to, in response to determining that the corrected current visual lane information is consistent with the current map lane information, generate target lane information corresponding to the current position.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner in the first aspect.

[0007] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation manner of the first aspect.

[0008] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the computer program implements the method described in any implementation manner in the first aspect.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is an exemplary system architecture diagram in which the present disclosure may be applied;

[0012] Figure 2 is a flow chart of an embodiment of a method for determining lane information according to the present disclosure;

[0013] Figure 3 is a flow chart of another embodiment of a method for determining lane information according to the present disclosure;

[0014] Figure 4 is a flow chart of another embodiment of a method for determining lane information according to the present disclosure;

[0015] Figure 5 yes Figure 4 A flowchart of step 406;

[0016] Figure 6 is a flow chart of another embodiment of a method for determining lane information according to the present disclosure;

[0017] Figure 7 is an application scenario diagram of the lane information determination method according to the present disclosure;

[0018] Figure 8 is a structural schematic diagram of an embodiment of a lane information determination device according to the present disclosure;

[0019] Fig. 9 It is a block diagram of an electronic device used to implement the method for determining lane information in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of a method for determining lane information or an apparatus for determining lane information of the present disclosure can be applied.

[0023] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, 104, a network 105, and a server 106. The network 105 is used to provide a medium for communication links between the terminal devices 101, 102, 103, 104 and the server 106. The network 105 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0024] The user can use the terminal devices 101, 102, 103, 104 to interact with the server 106 via the network 105 to receive or send information, etc. Various client applications can be installed on the terminal devices 101, 102, 103, 104.

[0025] Terminal devices 101, 102, 103, 104 may be hardware or software. When terminal devices 101, 102, 103, 104 are hardware, they may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc. When terminal devices 101, 102, 103, 104 are software, they may be installed in the above electronic devices. They may be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0026] The server 106 can provide various services. For example, the server 106 can analyze and process the current map lane information and the current visual lane information obtained from the terminal devices 101, 102, 103, and 104, and generate a processing result (such as target lane information).

[0027] It should be noted that the server 106 can be hardware or software. When the server 106 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server 106 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0028] It should be noted that the lane information determination method provided in the embodiment of the present disclosure is generally executed by the server 106 , and accordingly, the lane information determination device is generally disposed in the server 106 .

[0029] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0030] Continue to refer Figure 2 , which shows a process 200 of an embodiment of a method for determining lane information according to the present disclosure. The method for determining lane information comprises the following steps:

[0031] Step 201, determine the current map lane information corresponding to the current position of the vehicle from the high-precision map.

[0032] In this embodiment, the execution subject of the lane information determination method (for example Figure 1 The server 105 shown in the figure will first determine the current location information of the vehicle, for example, the location of the vehicle can be obtained in real time through the global positioning system (GPS) installed on the vehicle, thereby obtaining the current location information of the vehicle, that is, the latitude and longitude coordinate information. Of course, the real-time location information of the vehicle can also be obtained according to other methods, which are not specifically limited in this embodiment.

[0033] Then, the above-mentioned execution entity will match the current position information with the pre-built high-precision map to obtain the lane information corresponding to the current position from the high-precision map, that is, the current map lane information.

[0034] It should be noted that a high-precision map is a semantic map that uses SLAM (Simultaneous Localization and Mapping) / SFM (Structure from Motion) or other algorithms to fuse multiple sensor data to construct a high-precision three-dimensional point cloud map.

[0035] The execution subject obtains the road information and lane information corresponding to the current position by matching the current position information with the high-precision map, and obtains the lane information of the current map. The lane information of the current map may include: the road ID (Identity document) of the current road, which is the unique coding information of the current road, and the number of lanes of the current road, whether each lane is a solid line or a dotted line, etc.

[0036] Step 202, determining the current visual lane information corresponding to the current position from the visual image collected by the vehicle.

[0037] In this embodiment, the above-mentioned execution subject determines the current visual lane information corresponding to the current position from the visual image collected by the vehicle. While the GPS on the vehicle obtains the vehicle's position information in real time, the camera sensor on the vehicle collects images around the vehicle in real time. For example, the front-view camera can collect images in front of the vehicle, and the surround-view camera can collect images around the vehicle.

[0038] Then, the execution subject will determine the lane information of the current position from the collected image, specifically, determine from the image how many lane lines are included, and whether each lane line is a dashed line or a solid line. For example, the lane information seen from the visual image (i.e., the current visual lane information) is from left to right: solid line, dashed line, solid line, and the current lane is in the second lane.

[0039] It should be noted that since the collection of visual images will be affected by factors such as lighting, the current visual lane information may be inaccurate, for example, the lane line of the lane may be viewed as a dotted line instead of a solid line.

[0040] This embodiment does not limit the execution order of step 201 and step 202, that is, step 201 can be executed before step 202, step 201 can also be executed after step 202, and even step 201 can be executed simultaneously with step 202.

[0041] Step 203 , in response to determining that the current visual lane information is inconsistent with the current map lane information, the current visual lane information is corrected according to the lane information in the pre-built trajectory database to obtain the corrected current visual lane information.

[0042] In this embodiment, the above-mentioned execution entity will determine whether the current visual lane information is consistent with the current map lane information. If it is determined that they are inconsistent, the lane information in the pre-constructed trajectory database will be counted, and the current visual lane information will be corrected according to the lane information obtained by the statistics, so as to obtain the corrected current visual lane information.

[0043] Since the current visual lane information corresponding to the visual image may be affected by factors such as lighting, resulting in inaccurate results, the above-mentioned execution subject will compare the current map lane information and the current visual lane information after determining the current map lane information and the current visual lane information to determine whether the information is consistent. If they are inconsistent, the current visual lane information is considered inaccurate and needs to be corrected.

[0044] As an example, the current map lane information is: the lane lines of the current road from left to right are: solid line, dotted line, solid line. The current visual lane information is: the lane lines of the current road from left to right are: dotted line, dotted line, solid line. Comparing the two, it is determined that the lane line information contained in the two is inconsistent (the virtual and real information of the first lane line on the left is inconsistent), so it is determined that the lane information in the trajectory database needs to be used to correct the information of the first lane line on the left in the current visual lane information.

[0045] Here, the trajectory database is constructed based on the lane information of a large number of trajectory points, that is, the latitude and longitude coordinates of each trajectory point in the massive trajectory points, the lane ID of its location, the lane it is located in, and the visual information corresponding to each trajectory point are obtained. For example, the visual information includes: the first lane line is a solid line, the second lane line is a dotted line, and the third lane line is a solid line. Optionally, the visual information can also include the confidence level corresponding to each lane line information, for example, the first lane line is a solid line, and its corresponding confidence level is 0.9, the second lane line is a dotted line, and its corresponding confidence level is 0.4, and the third lane line is a solid line, and its corresponding confidence level is 0.2.

[0046] Then, the execution subject will count the information of the massive trajectory points obtained to construct a road lane image, which contains the statistical information corresponding to each result of each lane line in each lane of each road. Specifically, for each lane line contained in each road, the number corresponding to each result is counted from the visual information of the massive trajectory points.

[0047] For example, for the first lane of Road 1, the number of times the lane line of the lane is a dotted line is counted from the visual information of the massive trajectory points is 3, the number of times the lane line of the lane is a solid line is counted from the visual information of the massive trajectory points is 5, and the number of times the lane line of the lane is unknown is counted from the visual information of the massive trajectory points is 0. Then, the statistical features corresponding to Lane 1 of Road 1 are: dotted line: 3, solid line: 5, unknown: 0.

[0048] For another example, for the second lane of road N, the number of times the lane line of the lane is a dotted line is counted from the visual information of the massive trajectory points is 2, the number of times the lane line of the lane is a solid line is counted from the visual information of the massive trajectory points is 6, and the number of times the lane line of the lane is unknown is counted from the visual information of the massive trajectory points. Then, the statistical features corresponding to lane 2 of road N are: dotted lines: 2, solid lines: 6, unknown: 1.

[0049] By analogy, statistical information corresponding to each result of each lane line in each lane of each road can be obtained.

[0050] When the lane information in the trajectory database is used to correct the current visual lane information, it is assumed that the current map lane information is: the lane lines of the current road are from left to right: solid line, dotted line, solid line. The current visual lane information is: the lane lines of the current road are from left to right: dotted line, dotted line, solid line. Comparing the two, the first lane line information (dotted line) in the current visual lane information is inconsistent with the current map lane information (solid line). At this time, it can be determined that the lane line information to be corrected is the first lane line information. Then, based on the road ID of the current position, the statistical information of each result corresponding to the lane line to be corrected is obtained from the trajectory database, and then the lane line information with a large proportion of the results is determined as the target information, and the lane line information to be corrected in the current visual lane information is corrected to the target information, thereby obtaining the corrected current visual lane information.

[0051] As an example, based on the road ID of the current position, the statistical information of each result corresponding to the lane line to be corrected is obtained from the trajectory database: solid line: 8, dotted line: 2, unknown: 0. It can be seen that there are a total of 10 results for the lane lines to be corrected, of which solid line results account for 0.8 and dotted line results account for 0.2. Then it can be determined that the solid line result is the target result. At this time, the above-mentioned execution entity will correct the lane line information (dotted line) to be corrected in the current visual lane information to the target result (solid line), so that the corrected current visual lane information is: solid line, dotted line, solid line.

[0052] Step 204 , in response to determining that the corrected current visual lane information is consistent with the current map lane information, generating target lane information corresponding to the current position.

[0053] In this embodiment, the above-mentioned execution entity will determine whether the corrected current visual lane information and the current map lane information are consistent. If they are consistent, it is considered that the vehicle position information is accurate at this time. The above-mentioned execution entity can output the vehicle's final target lane information based on the vehicle position in the corrected current visual lane information (the lane the vehicle is in and the lane line information of each lane of the current road) and the road ID and other information in the current map lane information. The target lane information may include: the road ID of the road where the vehicle is located, the lane the vehicle is in and the lane line information of each lane of the current road.

[0054] Since visual image information can accurately reflect the environmental information near the vehicle and the information of other vehicles or obstacles, the executor generally uses visual image information to mine and plan the vehicle's trajectory. After correcting the current visual lane information, the accuracy of trajectory planning can be further improved.

[0055] In addition, if the corrected current visual lane information and the current map lane information are still inconsistent, it is considered that the location information acquisition of the current track is abnormal, and an error processing can be performed or the current track point can be filtered. This embodiment does not make specific limitations on this.

[0056] The lane information determination method provided by the disclosed embodiment first determines the current map lane information corresponding to the current position of the vehicle from the high-precision map; then determines the current visual lane information corresponding to the current position from the visual image collected by the vehicle; then, in response to determining that the current visual lane information is inconsistent with the current map lane information, the current visual lane information is corrected according to the lane information in the pre-constructed trajectory database to obtain the corrected current visual lane information; finally, in response to determining that the corrected current visual lane information is consistent with the current map lane information, the target lane information corresponding to the current position is generated. The lane information determination method in this embodiment, when the visual lane information does not match the map lane information, corrects the visual lane information through the lane information of the massive trajectory points in the trajectory database, and finally fuses the corrected visual lane information with the map lane information to generate the final lane information, which solves the problem of inaccurate visual recall, that is, solves the problem that due to the influence of factors such as light, the visual image can only see part of the lane information, which makes it impossible to accurately locate the specific lane of the vehicle and the information of each lane through pure visual information, thereby improving the accuracy of the lane information.

[0057] In addition, in the technical solutions involved in this disclosure, the acquisition, storage, use, processing, transportation, provision and disclosure of user personal information (such as vehicle trajectory information involved in this disclosure later) are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0058] Continue to refer Figure 3 , Figure 3 A process 300 of another embodiment of a method for determining lane information according to the present disclosure is shown. The method for determining lane information comprises the following steps:

[0059] Step 301, determine the current map lane information corresponding to the current position of the vehicle from the high-precision map.

[0060] Step 302, determining the current visual lane information corresponding to the current position from the visual image collected by the vehicle.

[0061] Steps 301-302 are basically consistent with steps 201-202 of the aforementioned embodiment. For specific implementation methods, reference may be made to the aforementioned description of steps 201-202, which will not be repeated here.

[0062] Step 303, in response to determining that the current visual lane information is inconsistent with the current map lane information, determining a target lane line.

[0063] In this embodiment, the execution subject of the lane information determination method (for example Figure 1 The server 105 shown in the figure will determine whether the current visual lane information is consistent with the current map lane information. If it is determined that the current visual lane information is inconsistent with the current map lane information, the lane line whose information is inconsistent with the current visual lane information and the current map lane information is determined, that is, the target lane line.

[0064] As an example, the current map lane information is: the lane lines of the current road from left to right are: solid line, dotted line, solid line. The current visual lane information is: the lane lines of the current road from left to right are: dotted line, dotted line, solid line. Comparing the two, it is determined that the lane line information contained in the two is inconsistent (the virtual and real information of the first lane line on the left is inconsistent), so the target lane line is determined to be the first lane line on the left.

[0065] Step 304 , correcting the attribute information of the target lane line in the current visual lane information according to the lane information in the trajectory database, to obtain corrected current visual lane information.

[0066] In this embodiment, the execution subject uses the lane information in the trajectory database to modify the attribute information of the target lane line in the current visual lane information, thereby obtaining the modified current visual lane information. The attribute information here can be the number of lane lines or the color of the lane lines.

[0067] For example, the current map lane information is: the lane lines of the current road from left to right are: solid line, dotted line, solid line. The current visual lane information is: the lane lines of the current road from left to right are: dotted line, dotted line, solid line. At this time, it can be determined that the color information of the first lane line on the left in the current visual lane information needs to be corrected.

[0068] For another example, the current map lane information is: the lane lines of the current road are from left to right: solid line, dotted line, solid line. The current visual lane information is: the lane lines of the current road are from left to right: dotted line, solid line. At this point, it can be determined that the number of lane lines in the current visual lane information needs to be corrected, and on this basis, the color of each lane line may need to be further corrected.

[0069] Here, the trajectory database is constructed based on the lane information of a large number of trajectory points, that is, the latitude and longitude coordinates of each trajectory point in the massive trajectory points, the lane ID of its location, the lane it is located in, and the visual information corresponding to each trajectory point are obtained. For example, the visual information includes: the first lane line is a solid line, the second lane line is a dotted line, and the third lane line is a solid line. Optionally, the visual information can also include the confidence level corresponding to each lane line information, for example, the first lane line is a solid line, and its corresponding confidence level is 0.9, the second lane line is a dotted line, and its corresponding confidence level is 0.4, and the third lane line is a solid line, and its corresponding confidence level is 0.2.

[0070] Then, the execution subject will count the information of the massive trajectory points obtained to construct a road lane image, which contains the statistical information corresponding to each result of each lane line in each lane of each road. Specifically, for each lane line contained in each road, the number corresponding to each result is counted from the visual information of the massive trajectory points.

[0071] For example, for the first lane of Road 1, the number of times the lane line of the lane is a dotted line is counted from the visual information of the massive trajectory points is 3, the number of times the lane line of the lane is a solid line is counted from the visual information of the massive trajectory points is 5, and the number of times the lane line of the lane is unknown is counted from the visual information of the massive trajectory points is 0. Then, the statistical features corresponding to Lane 1 of Road 1 are: dotted line: 3, solid line: 5, unknown: 0.

[0072] By analogy, statistical information corresponding to each result of each lane line in each lane of each road can be obtained.

[0073] When the lane information in the trajectory database is used to correct the current visual lane information, it is assumed that the current map lane information is: the lane lines of the current road are from left to right: solid line, dotted line, solid line. The current visual lane information is: the lane lines of the current road are from left to right: dotted line, dotted line, solid line. Comparing the two, the first lane line information (dotted line) in the current visual lane information is inconsistent with the current map lane information (solid line). At this time, it can be determined that the lane line information to be corrected is the first lane line information. Then, based on the road ID of the current position, the statistical information of each result corresponding to the lane line to be corrected is obtained from the trajectory database, and then the lane line information with a large proportion of the results is determined as the target information, and the lane line information to be corrected in the current visual lane information is corrected to the target information, thereby obtaining the corrected current visual lane information.

[0074] As an example, based on the road ID of the current position, the statistical information of each result corresponding to the lane line to be corrected is obtained from the trajectory database: solid line: 8, dotted line: 2, unknown: 0. It can be seen that there are a total of 10 results for the lane lines to be corrected, of which solid line results account for 0.8 and dotted line results account for 0.2. Then it can be determined that the solid line result is the target result. At this time, the above-mentioned execution entity will correct the lane line information (dotted line) to be corrected in the current visual lane information to the target result (solid line), so that the corrected current visual lane information is: solid line, dotted line, solid line.

[0075] Step 305 , in response to determining that the corrected current visual lane information is consistent with the current map lane information, generating target lane information corresponding to the current position.

[0076] Step 305 is basically the same as step 204 of the aforementioned embodiment. The specific implementation method can refer to the aforementioned description of step 204, which will not be repeated here.

[0077] from Figure 3 It can be seen that Figure 2 Compared with the corresponding embodiments, the method for determining lane information in this embodiment, when the visual lane information does not match the map lane information, first determines the inconsistent lane lines, and then uses the lane information of the massive trajectory points in the trajectory database to correct the visual lane information, thereby correcting the information of the target lane lines in the current visual lane information based on the visual information of the massive trajectory points, thereby improving the accuracy of the corrected current visual lane information, and further improving the accuracy of the target lane information.

[0078] Continue to refer Figure 4 , Figure 4 A process 400 of another embodiment of a method for determining lane information according to the present disclosure is shown. The method for determining lane information comprises the following steps:

[0079] Step 401, determine the current map lane information corresponding to the current position of the vehicle from the high-precision map.

[0080] Step 402, determining the current visual lane information corresponding to the current position from the visual image collected by the vehicle.

[0081] Step 403 , in response to determining that the current visual lane information is inconsistent with the current map lane information, determining a target lane line.

[0082] Steps 401-403 are basically consistent with steps 301-303 of the aforementioned embodiment. For specific implementation methods, reference may be made to the aforementioned description of steps 301-303, which will not be repeated here.

[0083] Step 404 , determining a lane consistency rate based on the visual lane information and the map lane information of each lane in the trajectory database.

[0084] In this embodiment, the execution subject of the lane information determination method (for example Figure 1 The server 105 shown in the figure will determine the lane consistency rate based on the visual lane information and map lane information of each lane in the trajectory database, wherein the lane consistency rate is used to characterize the consistency degree between the visual lane information and map lane information of all lanes in the trajectory database. That is, for the visual lane information of the massive trajectory points in the trajectory database, the above-mentioned execution subject will make an overall assessment of the accuracy of the visual lane information in the trajectory database.

[0085] Specifically, the execution entity will obtain the lane information of each trajectory point in the massive trajectory points, that is, the map lane information, from the high-precision map. Then the visual lane information of each trajectory point is compared with the map lane information to determine the information consistency rate. Here, after obtaining the information consistency rate of each trajectory point, the above-mentioned execution entity can take the average of the information consistency rates of all trajectory points to obtain the lane consistency rate; the comparison results of all trajectory points can also be summarized to generate the lane consistency rate based on the summary results. This embodiment does not specifically limit the specific method for generating the lane consistency rate.

[0086] In some optional implementations of this embodiment, step 404 includes: determining the number of consistent lane lines and the total number of lane lines in the visual lane information and map lane information of each lane; calculating the ratio of the number of consistent lane lines to the total number of lane lines to obtain a lane consistency rate.

[0087] In this implementation, the execution subject compares the visual lane information and the map lane information of each track point to determine the number of lane lines that are consistent in the visual lane information and the map lane information of each track point. And based on the number of lane lines included in the visual lane information and the map lane information of each track point, the total number of lane lines corresponding to the track point is generated, for example, the lane lines included in the visual lane information of the track point and the lane lines included in the map lane information are added and then the average is taken.

[0088] As an example, the trajectory database contains M trajectory points. For trajectory point 1, its corresponding visual lane information is: solid line, dotted line, solid line, and the map lane information is: dotted line, dotted line, solid line, that is, the number of lane lines that are consistent in the visual lane information and map lane information of trajectory point 1 is 2. The visual lane information of trajectory point 1 includes 3 lane lines, and the map lane information also includes 3 lane lines. Therefore, the total number of lane lines corresponding to trajectory point 1 is (3+3) / 2=3. Therefore, for trajectory point 1, the number of consistent lane lines is 2, and the total number of lane lines is 3.

[0089] As another example, for track point 2, its corresponding visual lane information is: dotted line, solid line, and the map lane information is: dotted line, dotted line, solid line, that is, the number of consistent lane lines in the visual lane information and map lane information of track point 2 is 2, the visual lane information of track point 2 includes 2 lane lines, and the map lane information includes 3 lane lines, so the total number of lane lines corresponding to track point 2 is (2+3) / 2=2.5. Thus, for track point 2, the number of consistent lane lines is 2, and the total number of lane lines is 2.5.

[0090] Then add up the number of consistent lane lines of all trajectory points to get the total number of consistent lane lines; add up the total number of lane lines corresponding to all trajectory points to get the total number of lane lines.

[0091] After determining the number of consistent lane lines and the total number of lane lines in the visual lane information and map lane information of each track point, the number of consistent lane lines corresponding to all track points is added together to obtain the total number of consistent lane lines for all track points in the track database. Then, the total number of lane lines corresponding to all track points is added together to obtain the total number of lane lines for all track points in the track database.

[0092] Finally, the ratio of the total number of consistent lane lines to the total number of lane lines is calculated to obtain the lane consistency rate C, that is, C can be expressed as: lane consistency rate C = total number of consistent lane lines / total number of lane lines.

[0093] For example, if the total number of consistent lane lines is 8000 and the total number of lane lines is 10000, the lane consistency rate C is 0.8. The lane consistency rate threshold is used to evaluate the accuracy of the visual lane information in the trajectory database. The larger C is, the higher the accuracy of the visual information in the trajectory database.

[0094] The lane consistency rate is calculated in the above manner, so that the accuracy of the visual lane information in the trajectory database can be evaluated as a whole through the lane consistency rate to obtain the corresponding evaluation result.

[0095] Step 405, determining the quantity ratio of each attribute information of the target lane line from the target visual lane information.

[0096] In this embodiment, the above-mentioned execution entity determines the quantity ratio of each attribute information of the target lane line from the target visual lane information, wherein the target visual lane information includes all visual lane information corresponding to the target lane line in the trajectory database.

[0097] That is, the above-mentioned execution subject will obtain the statistical results of various attribute information corresponding to the lane line to be corrected (i.e., the target lane line) from the trajectory database based on the road ID of the current position, for example, respectively obtain the result proportion of the target lane line being a solid line, and the result proportion of the target lane line being a dotted line. The quantity proportion Q can be expressed as: Q = lane line result / (count (lane line result 1) + count (lane line result 2) + ... + count (lane line result N)), where N represents the number of attribute results corresponding to the lane line, and count (lane line result N) represents the number corresponding to the current lane line result.

[0098] As an example, the statistical results of various attribute information corresponding to the target lane line obtained from the trajectory database are: solid line: 8, dotted line: 2, unknown: 0. According to the above calculation formula, the solid line result of the target lane line is Q=8 / (8+2+0)=0.8, and the dotted line result is Q=2 / (8+2+0)=0.2.

[0099] Step 406 , based on the relationship between the lane consistency rate and a preset consistency rate threshold and the relationship between the number share and a preset share threshold, determine whether the lane consistency rate and the number share meet preset requirements.

[0100] In this embodiment, the above-mentioned execution subject will pre-set a corresponding threshold for the lane consistency rate, that is, the consistency rate threshold, and set a corresponding threshold for the quantity proportion, that is, the proportion threshold. Then, the relationship between the calculated lane consistency rate and the consistency rate threshold is determined, and the relationship between the quantity proportion and the proportion threshold is determined. Finally, the consistency rate relationship and the proportion relationship are comprehensively considered to determine whether the lane consistency rate and the quantity proportion meet the preset requirements, wherein the preset requirements are used to characterize the degree of consistency between the lane information in the trajectory database and the lane information in the high-precision map. For example, when the lane consistency rate is greater than or equal to the consistency rate threshold and / or the quantity proportion is greater than the proportion threshold, it is determined that the lane consistency rate and the quantity proportion meet the preset requirements, indicating that the lane information in the trajectory database and the lane information in the high-precision map are highly consistent.

[0101] It should be noted that the proportion of each attribute information of each lane line in all the attribute information of the lane line has been calculated before. Therefore, when determining whether the lane consistency rate and quantity proportion meet the preset requirements, the average of all proportions and the proportion threshold can be used for judgment, and the average of all proportions can be used to evaluate the overall quantity proportion.

[0102] When the lane consistency rate is greater than or equal to the consistency rate threshold and the number proportion is greater than the proportion threshold, it is determined that the lane consistency rate and the number proportion meet the preset requirements.

[0103] By judging the relationship between the lane consistency rate and the preset consistency rate threshold and the relationship between the number share and the preset share threshold, the consistency degree between the lane information in the trajectory database and the lane information in the high-precision map can be determined, and the accuracy of the visual lane information in the trajectory database is proportional to the consistency degree. That is, when the lane consistency rate is greater than or equal to the consistency rate threshold and the number share is greater than the share threshold, it is determined that the accuracy of the visual lane information in the trajectory database is higher than the consistency degree, that is, the accuracy of the visual lane information in the trajectory database meets the requirements, thereby improving the accuracy of the subsequent correction of the current visual lane information using the lane information in the trajectory database.

[0104] Step 407, in response to determining that the lane consistency rate and the number ratio meet the preset requirements, the attribute information of the target lane line in the current visual lane information is corrected according to the attribute information of the target lane line in the target visual lane information to obtain the corrected current visual lane information.

[0105] In this embodiment, the above-mentioned execution subject will correct the attribute information of the target lane line in the current visual lane information according to the attribute information of the target lane line in the target visual lane information when it is determined that the lane consistency rate and the number ratio meet the preset requirements, so as to obtain the corrected current visual lane information. When the lane consistency rate and the number ratio meet the preset requirements, the information of the target lane line is corrected to improve the accuracy of the correction result.

[0106] Specifically, if it is determined that the lane consistency rate and the number ratio meet the preset requirements, the attribute information of the target lane line in the current visual lane information can be corrected according to the statistical results of the attribute information corresponding to the target lane line in the trajectory database, so as to obtain the corrected current visual lane information. Therefore, when the lane consistency rate and the number ratio meet the preset requirements, the attribute information of the target lane line in the current visual lane information is corrected according to the statistical results of the attribute information corresponding to the target lane line in the trajectory database, thereby improving the accuracy of the corrected visual lane information.

[0107] In some optional implementations of the present embodiment, the attribute information of the target lane line in the current visual lane information is corrected according to the attribute information of the target lane line in the target visual lane information, including: determining the target attribute information according to the quantity ratio of each attribute information of the target lane line; and correcting the attribute information of the target lane line in the current visual lane information to the target attribute information.

[0108] In this implementation, the attribute information with the largest proportion among the various attribute information of the target lane line will be determined as the target attribute information, and the attribute information of the target lane line in the current visual lane information will be corrected to the target attribute information. For example, for the target lane line, the solid line result accounts for 0.8, and the dotted line result accounts for 0.2, then the solid line is determined as the target attribute information. At this time, the above-mentioned execution subject will correct the target lane line information (dotted line) in the current visual lane information to the target result (solid line), so that the corrected current visual lane information is a solid line. In this way, the information of the target lane line is corrected to the attribute information with the highest proportion, which improves the accuracy of the corrected attribute information.

[0109] Step 408 , in response to determining that the corrected current visual lane information is consistent with the current map lane information, generating target lane information corresponding to the current position.

[0110] Step 408 is basically the same as step 204 in the aforementioned embodiment. For the specific implementation method, reference may be made to the aforementioned description of step 204 and will not be repeated here.

[0111] from Figure 4 It can be seen that Figure 3Compared with the corresponding embodiments, the method for determining lane information in this embodiment first determines the target lane line whose visual lane information does not match the map lane information, and then performs statistics on the attribute information of the target lane line in the trajectory database, and corrects the information of the target lane line to the attribute information with the highest proportion in the statistical results, thereby improving the accuracy of the corrected attribute information.

[0112] Continue to refer Figure 5 , Figure 5 Shows Figure 4 A specific process 500 of step 406 in FIG. 4 is shown in FIG. 4 . The matching step includes:

[0113] Step 501 , in response to the lane consistency rate being less than a first consistency rate threshold, determining that the lane consistency rate and the number ratio do not meet preset requirements.

[0114] Here, the preset consistency rate threshold includes a first consistency rate threshold. The lane consistency rate C is used to evaluate the accuracy of the visual lane information in the trajectory database, so the larger C is, the higher the accuracy of the visual lane information in the trajectory database is.

[0115] Therefore, if C is less than the first consistency rate threshold, it is considered that the accuracy of the visual lane information in the trajectory database is not enough. At this time, no matter what the value of Q is, the information in the trajectory database is not used to correct the information of the target lane line. In other words, if C is less than the first consistency rate threshold, no matter what the value of Q is, it is determined that the lane consistency rate and number ratio do not meet the preset requirements. At this time, the information in the trajectory database will not be used to correct the information of the target lane line.

[0116] Step 502 , in response to the lane consistency rate being greater than or equal to the first consistency rate threshold, it is determined whether the quantity proportion is greater than the first proportion threshold, and a first determination result is obtained.

[0117] The preset proportion threshold includes a first proportion threshold. Each attribute information has a quantity proportion in all attribute information corresponding to the lane line, and the quantity proportion Q is the average of all quantity proportions, so the larger the Q is, the higher the proportion of the attribute information is.

[0118] If C is greater than the first consistency rate threshold, it is considered that the accuracy of the visual lane information in the trajectory database meets the requirements. At this time, it will continue to determine whether the quantity proportion Q is greater than the first proportion threshold, thereby obtaining the corresponding first judgment result.

[0119] Here, the first consistency rate threshold may be set to 0.5, and the first proportion threshold may be set to 0.4. The first consistency rate threshold and the first proportion threshold may also be set according to actual conditions or relevant experience, and this embodiment does not specifically limit this.

[0120] Step 503: Determine whether the lane consistency rate and number ratio meet preset requirements based on the first judgment result.

[0121] After obtaining the first judgment result, it will be further determined based on the first result whether the lane consistency rate and quantity ratio meet the preset requirements, so as to determine whether to use the lane information in the trajectory database to correct the attribute information of the target lane line, thereby ensuring the accuracy of the corrected result.

[0122] In some optional implementations of this embodiment, the consistency rate threshold also includes: a second consistency rate threshold, the second consistency rate threshold is greater than the first consistency rate threshold, and determining whether the lane consistency rate and quantity ratio meet the preset requirements based on the first judgment result includes: in response to the first judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity ratio is greater than the first ratio threshold, determining that the lane consistency rate and quantity ratio meet the preset requirements; in response to the first judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity ratio is less than or equal to the first ratio threshold, judging whether the lane consistency rate is less than the second consistency rate threshold, and obtaining a second judgment result; determining whether the lane consistency rate and quantity ratio meet the preset requirements based on the second judgment result.

[0123] In this implementation, if the first judgment result is that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity ratio is greater than the first ratio threshold, then it is considered that the lane consistency rate and the quantity ratio of the attribute information meet the requirements, and the lane consistency rate and the quantity ratio are determined to match. At this time, the attribute information of the target lane line with the largest quantity ratio corresponding to the target lane line in the trajectory database is used to correct the attribute information of the target lane line.

[0124] If the first judgment result is that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity ratio is less than or equal to the first ratio threshold, then it is considered that the quantity ratio does not meet the requirement. At this time, it is necessary to determine whether the lane consistency rate is between the first consistency rate threshold and the second consistency rate threshold. Since the second consistency rate threshold is greater than the first consistency rate threshold, when the quantity ratio of the attribute information does not meet the preset requirement (i.e., it is not large enough), the lane consistency rate will be required to meet a higher accuracy requirement. Here, the second consistency rate threshold can be set to 0.75 (the first consistency rate threshold is 0.5), or it can be set to other values.

[0125] Therefore, at this time, it is determined whether the lane consistency rate is less than the second consistency rate threshold, thereby obtaining a second judgment result, and determining whether the lane consistency rate and quantity ratio meet the preset requirements based on the second judgment result.

[0126] That is, when the proportion of the number of attribute information does not meet the preset requirements (is not large enough), it will further determine whether the lane consistency rate meets higher accuracy requirements, thereby improving the matching degree between the lane consistency rate and the proportion of the number of attribute information, so as to ensure the accuracy of the correction based on the matching degree.

[0127] In some optional implementations of this embodiment, the proportion threshold further includes: a second proportion threshold, and the second proportion threshold is smaller than the first proportion threshold.

[0128] And determining whether the lane consistency rate and the number share meet the preset requirements based on the second judgment result, including: in response to the second judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and less than the second consistency rate threshold and the number share is less than or equal to the first share threshold, determining that the lane consistency rate and the number share do not meet the preset requirements; in response to the second judgment result that the lane consistency rate is greater than or equal to the second consistency rate threshold and the number share is less than the first share threshold, judging whether the number share is greater than the second share threshold to obtain a third judgment result; determining whether the lane consistency rate and the number share meet the preset requirements based on the third judgment result.

[0129] In this implementation, if the second judgment result is that the lane consistency rate is greater than or equal to the first consistency rate threshold and less than the second consistency rate threshold and the quantity ratio is not greater than the first ratio threshold, it means that the lane consistency rate meets the higher accuracy requirement, but the quantity ratio of the attribute information is not high enough. At this time, it is considered that the lane consistency rate and the quantity ratio do not match, that is, the attribute information of the target lane line in the trajectory database is not used to correct the attribute information of the target lane line.

[0130] If the second judgment result is that the lane consistency rate is greater than or equal to the second consistency rate threshold and the number ratio is less than the first ratio threshold, then it will be further judged whether the number ratio is greater than the second ratio threshold and the second ratio threshold is less than the first ratio threshold, so as to judge whether the number ratio meets the requirements, thereby obtaining the third judgment result, and determining whether the lane consistency rate and number ratio match according to the third judgment result. Here, the second ratio threshold can be set to 0.3 (the first ratio threshold is 0.4).

[0131] That is, when the lane consistency rate reaches a sufficiently large value, the requirement for the quantity ratio can be lowered to determine whether the quantity ratio is between the first ratio threshold and the second ratio threshold, thereby improving the matching degree between the lane consistency rate and the quantity ratio of the attribute information, and ensuring the accuracy of the correction based on the matching degree.

[0132] In some optional implementations of this embodiment, whether the lane consistency rate and the number share meet the preset requirements is determined based on the third judgment result, including: in response to the third judgment result that the number share is less than the first share threshold and greater than or the second share threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, determining that the lane consistency rate and the number share match; in response to the third judgment result that the number share is less than or equal to the second share threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, determining that the lane consistency rate and the number share do not meet the preset requirements.

[0133] In this implementation, if the third judgment result is that the quantity ratio is less than the first ratio threshold and greater than the second ratio threshold, and the lane consistency rate is greater than or equal to the second consistency rate threshold, then it is considered that both the lane consistency rate and the quantity ratio meet the preset requirements, and it is determined that the lane consistency rate and the quantity ratio match.

[0134] If the third judgment result is that the quantity ratio is less than or equal to the second ratio threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, at this time, it is considered that the quantity ratio does not meet the preset requirements, and it is determined that the lane consistency rate and the quantity ratio do not match, that is, the attribute information of the target lane line in the trajectory database is not used to correct the attribute information of the target lane line.

[0135] In summary, taking the first consistency rate threshold as 0.5, the second consistency rate threshold as 0.75, the first proportion threshold as 0.4, and the second proportion threshold as 0.3 as an example, the following table clearly shows the matching relationship between the lane consistency rate C and the number proportion Q:

[0136] Table 1 Matching relationship between lane consistency rate and number ratio

[0137] C Q Match <0.5 Any value no >＝0.5 >0.4 yes >=0.5 and <0.75 <＝0.4 no >＝0.75 >0.3 and <0.4 yes >＝0.75 <＝0.3 no

[0138] Through the above steps, it is determined whether the lane consistency rate and the proportion of the number of attribute information meet the corresponding requirements. If both are met, the attribute information is used to correct the attribute information of the target lane line, so as to ensure the accuracy of the corrected attribute information.

[0139] Continue to refer Figure 6 , Figure 6 A process 600 of another embodiment of a method for determining lane information according to the present disclosure is shown. The method for determining lane information comprises the following steps:

[0140] Step 601, determine the lane ID of the lane where the vehicle is located from the high-precision map based on the current position.

[0141] In this embodiment, the execution subject of the lane information determination method (for example Figure 1The server 105 shown in the figure will first determine the current location information of the vehicle, for example, the location of the vehicle can be obtained in real time through the GPS installed on the vehicle, thereby obtaining the current location information of the vehicle, that is, the latitude and longitude coordinate information. Then, the above-mentioned execution entity will match the current location information with the pre-built high-precision map to obtain the lane information corresponding to the current location from the high-precision map, that is, the current map lane information. The current map lane information may include: the road ID information of the current road.

[0142] Step 602, determine the map lane line information from the high-precision map according to the lane ID.

[0143] In this embodiment, the execution subject will match the lane line information of the lane where the vehicle is located from the high-precision map according to the road ID of the current road, for example, the number of lanes included in the current road, whether each lane is a solid line or a dashed line, etc., so as to obtain the lane line information of the current map, that is, the lane information of the current map includes: lane ID and map lane line information, and the map lane line information includes the number of lane lines and / or the color of lane lines. Thus, the road network information of the vehicle's current position is obtained from the high-precision map based on the vehicle's current position.

[0144] Step 603, recognize the visual image, determine the lane line information corresponding to the current position, and record the lane line information corresponding to the current position as the visual lane line information.

[0145] In this embodiment, the above-mentioned execution subject will perform image recognition on the visual image to determine the lane line information corresponding to the current position and obtain the current visual lane line information. The current visual lane information includes: visual lane line information, and the visual lane line information is the number information of the lane lines and / or the virtual and real information of the lane lines. Specifically, determine from the image how many lane lines are included, and whether each lane line is a dotted line or a solid line. For example, the lane information obtained based on the recognition of the visual image (i.e., the current visual lane information) is from left to right: solid line, dotted line, solid line, and the current lane is located in the second lane. Thus, by recognizing the visual image, the visual lane information of its position can be obtained.

[0146] Step 604 , in response to determining that the current visual lane information is inconsistent with the current map lane information, the current visual lane information is corrected according to the lane information in the pre-constructed trajectory database to obtain corrected current visual lane information.

[0147] Step 604 is basically the same as step 203 of the aforementioned embodiment. The specific implementation method can refer to the aforementioned description of step 203, which will not be repeated here.

[0148] Step 605 , in response to determining that the corrected current visual lane information is consistent with the current map lane information, the corrected current visual lane information and the current map lane information are merged to generate target lane information.

[0149] In this embodiment, the above-mentioned execution entity will respond to determining that the corrected current visual lane information is consistent with the current map lane information, merge the corrected current visual lane information and the current map lane information, and generate target lane information, wherein the target lane information includes: lane ID and visual lane line information in the corrected current visual lane information.

[0150] Specifically, the above-mentioned execution entity will determine whether the corrected current visual lane information and the current map lane information are consistent. If they are consistent, it is considered that the vehicle position information is accurate at this time. The above-mentioned execution entity can output the vehicle's final target lane information based on the vehicle position in the corrected current visual lane information (the lane the vehicle is in and the lane line information of each lane of the current road) and the road ID and other information in the current map lane information. The target lane information may include: the road ID of the road where the vehicle is located, the lane the vehicle is in and the lane line information of each lane of the current road.

[0151] Since visual image information can accurately reflect the environmental information near the vehicle and the information of other vehicles or obstacles, the executor generally uses visual image information to mine and plan the vehicle's trajectory. After correcting the current visual lane information, the accuracy of trajectory planning can be further improved.

[0152] In addition, if the corrected current visual lane information and the current map lane information are still inconsistent, it is considered that the location information acquisition of the current track is abnormal, and an error processing can be performed or the current track point can be filtered. This embodiment does not make specific limitations on this.

[0153] from Figure 6 It can be seen that Figure 2 Compared with the corresponding embodiments, the method for determining lane information in this embodiment highlights the steps of determining map lane information and visual lane information, and when the corrected current visual lane information is consistent with the current map lane information, the corrected current visual lane information and the current map lane information are merged to generate target lane information, thereby further improving the accuracy of the target lane information.

[0154] Continue to refer Figure 7 , Figure 7An application scenario of the lane information determination method according to the present disclosure is shown. In this application scenario, the execution subject extracts visual information 702 of the current position from the visual image 701 collected by the camera sensor of the vehicle. The visual information is: the lane lines from left to right are Dash (8), Dash (8), Solid (3), where Dash represents a dotted line, 8 represents the coding information of the dotted line, Solid represents a solid line, and 3 represents the coding information of the solid line. At the same time, the map information 704 of the current position is determined from the high-precision map 703. The map information is: the first lane line is a solid line, the second lane line is a dotted line, and the third lane line is a solid line.

[0155] Then, the execution subject will determine whether the visual information 702 and the map information 703 are consistent. After determination, if the information of the first lane line is inconsistent, the first lane line will be determined as the target lane line 705.

[0156] Afterwards, for all lane line information in the pre-built trajectory database, the lane consistency rate 706 and the mean value of the proportion of the lane line attribute information - the number proportion 707 are calculated, and when the lane consistency rate matches the number proportion, the attribute information with the highest proportion among the attribute information corresponding to the target lane line is determined as the target attribute information, and the attribute information of the target lane line is corrected to the target attribute information, thereby obtaining the corrected visual information 708. For example, the solid line has the highest proportion, so the solid line is determined as the target attribute information, and the attribute information of the target lane line is corrected to the target attribute information (solid line), and the corrected visual information is: Solid (3), Dash (8), Solid (3).

[0157] Finally, make sure that the corrected visual information (Solid, Dash, Solid) is consistent with the map information (the first lane line is a solid line, the second lane line is a dotted line, and the third lane line is a solid line). At this time, combine the road ID and other information in the map information 704 with the visual lane information in the corrected attribute information 708 to generate the target information 709 of the current position.

[0158] Further references Figure 8 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a lane information determination device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0159] like Figure 8As shown, the lane information determination device 800 of this embodiment includes: a map information determination module 801, a visual information determination module 802, an information correction module 803 and a target information determination module 804. Among them, the map information determination module 801 is configured to determine the current map lane information corresponding to the current position of the vehicle from the high-precision map; the visual information determination module 802 is configured to determine the current visual lane information corresponding to the current position from the visual image collected by the vehicle; the information correction module 803 is configured to correct the current visual lane information according to the lane information in the pre-constructed trajectory database in response to determining that the current visual lane information is inconsistent with the current map lane information, and obtain the corrected current visual lane information; the target information determination module 804 is configured to generate the target lane information corresponding to the current position in response to determining that the corrected current visual lane information is consistent with the current map lane information.

[0160] In the lane information determination device 800, the specific processing of the map information determination module 801, the visual information determination module 802, the information correction module 803 and the target information determination module 804 and the technical effects thereof can be referred to in detail. Figure 2 The relevant descriptions of steps 201 - 204 in the corresponding embodiment are not repeated here.

[0161] In some optional implementations of the present embodiment, the information correction module includes: a lane line determination submodule, configured to determine a target lane line in response to determining that the current visual lane information is inconsistent with the current map lane information, wherein the target lane line is a lane line whose information is inconsistent with the current visual lane information and the current map lane information; an information correction submodule, configured to correct the attribute information of the target lane line in the current visual lane information according to the lane information in the trajectory database.

[0162] In some optional implementations of the present embodiment, the information correction submodule includes: a consistency rate determination unit, configured to determine the lane consistency rate based on the visual lane information and map lane information of each lane in the trajectory database, wherein the lane consistency rate is used to characterize the consistency degree of the visual lane information and the map lane information of all lanes in the trajectory database; a proportion determination unit, configured to determine the quantity proportion of each attribute information of the target lane line from the target visual lane information, wherein the target visual lane information includes all visual lane information corresponding to the target lane line in the trajectory database; a correction unit, configured to correct the attribute information of the target lane line in the current visual lane information according to the attribute information of the target lane line in the target visual lane information in response to determining that the lane consistency rate and the quantity proportion meet the preset requirements.

[0163] In some optional implementations of this embodiment, the consistency rate determination unit is further configured to: determine the number of consistent lane lines and the total number of lane lines in the visual lane information and map lane information of each lane; calculate the ratio of the number of consistent lane lines to the total number of lane lines to obtain the lane consistency rate.

[0164] In some optional implementations of the present embodiment, the lane information determination device 800 further includes: a matching module, configured to determine whether the lane consistency rate and the quantity proportion meet preset requirements based on the relationship between the lane consistency rate and a preset consistency rate threshold and the relationship between the quantity proportion and a preset proportion threshold, wherein the preset requirements are used to characterize the degree of consistency between the lane information in the trajectory database and the lane information in the high-precision map.

[0165] In some optional implementations of this embodiment, the consistency rate threshold includes: a first consistency rate threshold; the proportion threshold includes: a first proportion threshold; and the matching module includes: a determination submodule, configured to determine that the lane consistency rate and the quantity proportion do not meet the preset requirements in response to the lane consistency rate being less than the first consistency rate threshold; a judgment submodule, configured to judge whether the quantity proportion is greater than the first proportion threshold in response to the lane consistency rate being greater than or equal to the first consistency rate threshold, to obtain a first judgment result; and a matching submodule, configured to determine whether the lane consistency rate and the quantity proportion meet the preset requirements based on the first judgment result.

[0166] In some optional implementations of this embodiment, the consistency rate threshold also includes: a second consistency rate threshold, the second consistency rate threshold is greater than the first consistency rate threshold; and the matching submodule includes: a determination unit, configured to determine that the lane consistency rate and the quantity share meet the preset requirements in response to the first judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity share is greater than the first share threshold; a judgment unit, configured to determine whether the lane consistency rate is less than the second consistency rate threshold in response to the first judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity share is less than or equal to the first share threshold, and obtain a second judgment result; a matching unit, configured to determine whether the lane consistency rate and the quantity share meet the preset requirements based on the second judgment result.

[0167] In some optional implementations of this embodiment, the proportion threshold also includes: a second proportion threshold, the second proportion threshold is less than the first proportion threshold; and the matching unit includes: a determination subunit, configured to determine that the lane consistency rate and the quantity proportion do not meet the preset requirements in response to the second judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and less than the second consistency rate threshold and the quantity proportion is less than or equal to the first proportion threshold; a judgment subunit, configured to judge whether the quantity proportion is greater than the second proportion threshold in response to the second judgment result that the lane consistency rate is greater than or equal to the second consistency rate threshold and the quantity proportion is less than the first proportion threshold, and obtain a third judgment result; a matching subunit, configured to determine whether the lane consistency rate and the quantity proportion meet the preset requirements based on the third judgment result.

[0168] In some optional implementations of this embodiment, the matching subunit is further configured to: in response to the third judgment result that the quantity ratio is less than the first proportion threshold and greater than the second proportion threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, determine that the lane consistency rate and the quantity ratio meet the preset requirements; in response to the third judgment result that the quantity ratio is less than or equal to the second proportion threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, determine that the lane consistency rate and the quantity ratio do not meet the preset requirements.

[0169] In some optional implementations of this embodiment, the correction unit is further configured to: determine the target attribute information based on the quantity ratio of each attribute information of the target lane line; and correct the attribute information of the target lane line in the current visual lane information into the target attribute information.

[0170] In some optional implementations of this embodiment, the current map lane information includes: lane ID and map lane line information; and the map information determination module is further configured to: determine the lane ID of the lane in which the vehicle is located from the high-precision map based on the current position; and determine the map lane line information from the high-precision map based on the lane ID.

[0171] In some optional implementations of this embodiment, the current visual lane information includes: visual lane line information; and the visual information determination module is further configured to: recognize the visual image to determine the lane line information corresponding to the current position; and record the lane line information corresponding to the current position as the visual lane line information.

[0172] In some optional implementations of this embodiment, the target information determination module is further configured to: in response to determining that the corrected current visual lane information is consistent with the current map lane information, fuse the corrected current visual lane information and the current map lane information to generate target lane information, wherein the target lane information includes: lane ID and visual lane line information in the corrected current visual lane information.

[0173] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0174] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0175] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0176] Multiple components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0177] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as the method for determining lane information. For example, in some embodiments, the method for determining lane information may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the method for determining lane information described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the method for determining lane information in any other appropriate manner (e.g., by means of firmware).

[0178] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0179] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable lane information determination device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0180] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0181] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0182] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0183] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0184] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0185] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for determining lane information, comprising: Determine the current map lane information corresponding to the current position of the vehicle from the high-precision map; Determining current visual lane information corresponding to the current position from the visual image collected by the vehicle; In response to determining that the current visual lane information is inconsistent with the current map lane information, the current visual lane information is corrected according to lane information in a pre-constructed trajectory database to obtain corrected current visual lane information; In response to determining that the corrected current visual lane information is consistent with the current map lane information, target lane information corresponding to the current position is generated.

2. The method according to claim 1, wherein: In response to determining that the current visual lane information is inconsistent with the current map lane information, the current visual lane information is corrected according to lane information in a pre-constructed trajectory database, including: In response to determining that the current visual lane information is inconsistent with the current map lane information, determining a target lane line, wherein the target lane line is a lane line where information in the current visual lane information and the current map lane information is inconsistent; The attribute information of the target lane line in the current visual lane information is corrected according to the lane information in the trajectory database.

3. The method according to claim 2, wherein: The modifying the attribute information of the target lane line in the current visual lane information according to the lane information in the trajectory database includes: Determining a lane consistency rate according to the visual lane information and the map lane information of each lane in the trajectory database, wherein the lane consistency rate is used to characterize the consistency degree between the visual lane information and the map lane information of all lanes in the trajectory database; Determine the quantity ratio of each attribute information of the target lane line from the target visual lane information, wherein the target visual lane information includes all visual lane information corresponding to the target lane line in the trajectory database; In response to determining that the lane consistency rate and the number proportion meet preset requirements, the attribute information of the target lane line in the current visual lane information is corrected according to the attribute information of the target lane line in the target visual lane information.

4. The method according to claim 3, wherein: Determining the lane consistency rate according to the visual lane information and the map lane information of each lane in the trajectory database includes: Determining the number of lane lines that are consistent in the visual lane information and the map lane information for each lane and the total number of lane lines; The ratio of the number of consistent lane lines to the total number of lane lines is calculated to obtain the lane consistency rate.

5. The method according to claim 3, further comprising: According to the relationship between the lane consistency rate and the preset consistency rate threshold and the relationship between the quantity share and the preset share threshold, determine whether the lane consistency rate and the quantity share meet the preset requirements, wherein the preset requirements are used to characterize the degree of consistency between the lane information in the trajectory database and the lane information in the high-precision map.

6. The method according to claim 5, wherein: The consistency rate threshold includes: a first consistency rate threshold; the proportion threshold includes: a first proportion threshold; and The determining, based on the relationship between the lane consistency rate and a preset consistency rate threshold and the relationship between the number proportion and a preset proportion threshold, whether the lane consistency rate and the number proportion meet the preset requirement includes: In response to the lane consistency rate being less than the first consistency rate threshold, determining that the lane consistency rate and the number proportion do not meet the preset requirement; In response to the lane consistency rate being greater than or equal to the first consistency rate threshold, determining whether the quantity proportion is greater than the first proportion threshold, and obtaining a first determination result; Determine whether the lane consistency rate and the quantity proportion meet the preset requirements according to the first judgment result.

7. The method according to claim 6, wherein: The consistency rate threshold further includes: a second consistency rate threshold, the second consistency rate threshold being greater than the first consistency rate threshold; and The determining, according to the first judgment result, whether the lane consistency rate and the number ratio meet the preset requirement includes: In response to the first judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and the number proportion is greater than the first proportion threshold, determining that the lane consistency rate and the number proportion meet the preset requirement; In response to the first judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and the number proportion is less than or equal to the first proportion threshold, determining whether the lane consistency rate is less than the second consistency rate threshold to obtain a second judgment result; Determine whether the lane consistency rate and the quantity proportion meet the preset requirements according to the second judgment result.

8. The method according to claim 7, wherein: The proportion threshold further includes: a second proportion threshold, the second proportion threshold is smaller than the first proportion threshold; and The determining, according to the second judgment result, whether the lane consistency rate and the number ratio meet the preset requirement includes: In response to the second judgment result that the lane consistency rate is greater than or equal to the first consistency rate threshold and less than the second consistency rate threshold and the number proportion is less than or equal to the first proportion threshold, determining that the lane consistency rate and the number proportion do not meet the preset requirement; In response to the second judgment result that the lane consistency rate is greater than or equal to the second consistency rate threshold and the number proportion is less than the first proportion threshold, determining whether the number proportion is greater than the second proportion threshold to obtain a third judgment result; Determine whether the lane consistency rate and the quantity ratio meet the preset requirements according to the third judgment result.

9. The method according to claim 8, wherein: The determining, according to the third judgment result, whether the lane consistency rate and the number ratio meet the preset requirement includes: In response to the third judgment result that the number proportion is less than the first proportion threshold and greater than the second proportion threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, determining that the lane consistency rate and the number proportion meet the preset requirement; In response to the third judgment result that the quantity proportion is less than or equal to the second proportion threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, it is determined that the lane consistency rate and the quantity proportion do not meet the preset requirement.

10. The method according to claim 3, wherein: The modifying the attribute information of the target lane line in the current visual lane information according to the attribute information of the target lane line in the target visual lane information includes: Determining target attribute information according to the quantity ratio of each attribute information of the target lane line; The attribute information of the target lane line in the current visual lane information is corrected to the target attribute information.

11. The method according to claim 1, wherein: The current map lane information includes: lane ID and map lane line information; and The determining of the current map lane information corresponding to the current position of the vehicle from the high-precision map includes: Determining a lane ID of a lane in which the vehicle is located from the high-precision map according to the current position; The map lane line information is determined from the high-precision map according to the lane ID.

12. The method according to claim 11, wherein: The current visual lane information includes: visual lane line information; and The determining the current visual lane information corresponding to the current position from the visual image collected by the vehicle includes: Recognize the visual image to determine lane line information corresponding to the current position; The lane line information corresponding to the current position is recorded as the visual lane line information.

13. The method according to claim 12, wherein: In response to determining that the corrected current visual lane information is consistent with the current map lane information, generating target lane information corresponding to the current position includes: In response to determining that the corrected current visual lane information is consistent with the current map lane information, the corrected current visual lane information and the current map lane information are fused to generate the target lane information, wherein the target lane information includes: the lane ID and the visual lane line information in the corrected current visual lane information.

14. A lane information determination device, comprising: A map information determination module is configured to determine current map lane information corresponding to the current position of the vehicle from the high-precision map; a visual information determination module, configured to determine current visual lane information corresponding to the current position from the visual image collected by the vehicle; an information correction module, configured to correct the current visual lane information according to lane information in a pre-constructed trajectory database in response to determining that the current visual lane information is inconsistent with the current map lane information, to obtain corrected current visual lane information; The target information determination module is configured to generate target lane information corresponding to the current position in response to determining that the corrected current visual lane information is consistent with the current map lane information.

15. The device according to claim 14, wherein: The information correction module comprises: A lane line determination submodule is configured to determine a target lane line in response to determining that the current visual lane information is inconsistent with the current map lane information, wherein the target lane line is a lane line whose information in the current visual lane information and the current map lane information is inconsistent; The information correction submodule is configured to correct the attribute information of the target lane line in the current visual lane information according to the lane information in the trajectory database.

16. The device according to claim 15, wherein: The information correction submodule comprises: a consistency rate determination unit configured to determine a lane consistency rate based on the visual lane information and the map lane information of each lane in the trajectory database, wherein the lane consistency rate is used to characterize the consistency degree between the visual lane information and the map lane information of all lanes in the trajectory database; A proportion determination unit is configured to determine the quantity proportion of each attribute information of the target lane line from the target visual lane information, wherein the target visual lane information includes all visual lane information corresponding to the target lane line in the trajectory database; The correction unit is configured to correct the attribute information of the target lane line in the current visual lane information according to the attribute information of the target lane line in the target visual lane information in response to determining that the lane consistency rate and the number proportion meet the preset requirements.

17. The device according to claim 16, wherein: The consistency rate determination unit is further configured to: Determining the number of lane lines that are consistent in the visual lane information and the map lane information for each lane and the total number of lane lines; The ratio of the number of consistent lane lines to the total number of lane lines is calculated to obtain the lane consistency rate.

18. The apparatus according to claim 16, further comprising: The matching module is configured to determine whether the lane consistency rate and the number proportion meet the preset requirements based on the relationship between the lane consistency rate and a preset consistency rate threshold and the relationship between the number proportion and a preset proportion threshold, wherein the preset requirements are used to characterize the degree of consistency between the lane information in the trajectory database and the lane information in the high-precision map.

19. The device according to claim 18, wherein: The consistency rate threshold includes: a first consistency rate threshold; the proportion threshold includes: a first proportion threshold; and The matching module comprises: a determination submodule, configured to, in response to the lane consistency rate being less than the first consistency rate threshold, determine that the lane consistency rate and the number proportion do not meet the preset requirement; a judgment submodule, configured to judge whether the number proportion is greater than the first proportion threshold in response to the lane consistency rate being greater than or equal to the first consistency rate threshold, and obtain a first judgment result; The matching submodule is configured to determine whether the lane consistency rate and the quantity proportion meet the preset requirements according to the first judgment result.

20. The device according to claim 19, wherein The consistency rate threshold further includes: a second consistency rate threshold, the second consistency rate threshold being greater than the first consistency rate threshold; and The matching submodule includes: a determining unit configured to, in response to the first judgment result being that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity proportion is greater than the first proportion threshold, determine that the lane consistency rate and the quantity proportion meet the preset requirement; a judgment unit configured to, in response to the first judgment result being that the lane consistency rate is greater than or equal to the first consistency rate threshold and the quantity proportion is less than or equal to the first proportion threshold, judge whether the lane consistency rate is less than the second consistency rate threshold, and obtain a second judgment result; The matching unit is configured to determine whether the lane consistency rate and the quantity proportion meet the preset requirements according to the second judgment result.

21. The device according to claim 20, wherein: The proportion threshold further includes: a second proportion threshold, the second proportion threshold is smaller than the first proportion threshold; and The matching unit comprises: a determination subunit configured to, in response to the second judgment result being that the lane consistency rate is greater than or equal to the first consistency rate threshold and less than the second consistency rate threshold and the quantity proportion is less than or equal to the first proportion threshold, determine that the lane consistency rate and the quantity proportion do not meet the preset requirement; a judgment subunit configured to, in response to the second judgment result being that the lane consistency rate is greater than or equal to the second consistency rate threshold and the number proportion is less than the first proportion threshold, judge whether the number proportion is greater than the second proportion threshold, and obtain a third judgment result; The matching subunit is configured to determine whether the lane consistency rate and the quantity proportion meet the preset requirements according to the third judgment result.

22. The device according to claim 21, wherein The matching subunit is further configured to: In response to the third judgment result that the number proportion is less than the first proportion threshold and greater than the second proportion threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, determining that the lane consistency rate and the number proportion meet the preset requirement; In response to the third judgment result that the quantity proportion is less than or equal to the second proportion threshold and the lane consistency rate is greater than or equal to the second consistency rate threshold, it is determined that the lane consistency rate and the quantity proportion do not meet the preset requirement.

23. The device according to claim 16, wherein: The correction unit is further configured to: Determining target attribute information according to the quantity ratio of each attribute information of the target lane line; The attribute information of the target lane line in the current visual lane information is corrected to the target attribute information.

24. The device according to claim 14, wherein: The current map lane information includes: lane ID and map lane line information; and The map information determination module is further configured to: Determining a lane ID of a lane in which the vehicle is located from the high-precision map according to the current position; The map lane line information is determined from the high-precision map according to the lane ID.

25. The device according to claim 24, wherein: The current visual lane information includes: visual lane line information; and The visual information determination module is further configured to: Recognize the visual image to determine lane line information corresponding to the current position; The lane line information corresponding to the current position is recorded as the visual lane line information.

26. The device according to claim 25, wherein The target information determination module is further configured to: In response to determining that the corrected current visual lane information is consistent with the current map lane information, the corrected current visual lane information and the current map lane information are fused to generate the target lane information, wherein the target lane information includes: the lane ID and the visual lane line information in the corrected current visual lane information.

27. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.

28. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method of any one of claims 1-13.

29. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 13.

Images